EgoEngine transforms egocentric human videos into high-fidelity robot data enabling zero-shot visuomotor dexterous policy learning without real-robot demonstrations.
Rsl-rl: A learning library for robotics research,
28 Pith papers cite this work. Polarity classification is still indexing.
28
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
CoP tactile representation with differentiable calibration enables zero-shot sim-to-real transfer and outperforms binary and raw-taxel baselines on peg-in-hole insertion and ball balancing with a multi-fingered hand.
Betting mechanisms can yield provably more accurate and efficient estimates of real-world robot behavior than Monte Carlo sampling under specified conditions, with practical approximations demonstrated on synthetic data and a robotic manipulator task.
HALO learns latent reduced-order models with Poincaré maps for hybrid locomotion dynamics, allowing Lyapunov-based regions of attraction to be lifted from latent space to the full-order system.
BRRL derives an analytic optimal policy for regularized constrained RL that guarantees monotonic improvement and yields the BPO algorithm that matches or exceeds PPO.
Foot-mounted proximity sensors provide pre-contact feedback that, when integrated into RL, improves quadruped traversal robustness on discrete terrain with reliable sim-to-real transfer.
MAPL trains quadruped locomotion policies from LLM-generated multi-objective trajectory preferences and matches or exceeds expert-designed reward performance in four environments without manual reward engineering.
Learns rotation-aware point-cloud embeddings calibrated to SO(3) geodesic error, enabling model-free RL for vision-based in-hand reorientation without pose or flow inputs.
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
HORIZON is a recoverability-governed checkpointed frontier curriculum for on-policy physical-domain scaling on quadruped locomotion that identifies three regularities: uneven widening, non-monotonic composition, and the necessity of joint on-policy interaction.
A quadruped robot with a three-degree-of-freedom active spine reaches 6.9 m/s top speed and 7.2 rad/s turning rate via an RL framework that rewards spine engagement and gallop gaits.
A framework using 3D Gaussian Splatting for visual domain randomization enables robust monocular RGB-based dexterous in-hand reorientation on real hardware for multiple objects under varied lighting.
PriPG-RL trains RL policies for POMDPs by distilling knowledge from a privileged anytime-feasible MPC planner into a P2P-SAC policy, improving sample efficiency and performance in partially observable robotic navigation.
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
SERNF fine-tunes dexterous manipulation policies on real hardware by pairing normalizing-flow policies with action-chunked critics and conservative off-policy RL.
Isaac Lab is a unified GPU-native platform combining high-fidelity physics, photorealistic rendering, multi-frequency sensors, domain randomization, and learning pipelines for scalable multi-modal robot policy training.
RANDPOL achieves effective quadruped locomotion by training only the final linear readout of a randomly initialized and fixed neural network policy, matching PPO results with reduced parameters and enabling zero-shot sim-to-real transfer on Unitree Go2.
PPO-EAL integrates exact augmented Lagrangian optimization into PPO for safe robotic control, with claimed theoretical guarantees and better empirical safety-performance tradeoffs on several robot benchmarks including sim-to-real gear assembly.
CTS-MoE combines a dense MoE actor with perception-based gating and a multi-critic architecture to enable adaptive perceptive locomotion on discontinuous terrain in a single-stage teacher-student training setup.
Redesigned regularization addresses implementation gaps in policy smoothing for RL, yielding smoother motions with improved performance and robustness on a quadruped robot in sim-to-real settings.
MARCH combines simplified-model trajectory generation with CLF-guided teacher RL and vision-policy distillation to enable stable humanoid locomotion over sparse terrain with better sample efficiency than pure model-free methods.
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.
Targeted changes to policy initialization, critic targets, and return estimation let SAC match PPO performance across legged locomotion tasks in massively parallel simulation.
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
citing papers explorer
-
EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations
EgoEngine transforms egocentric human videos into high-fidelity robot data enabling zero-shot visuomotor dexterous policy learning without real-robot demonstrations.
-
Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation
CoP tactile representation with differentiable calibration enables zero-shot sim-to-real transfer and outperforms binary and raw-taxel baselines on peg-in-hole insertion and ball balancing with a multi-fingered hand.
-
Betting for Sim-to-Real Performance Evaluation
Betting mechanisms can yield provably more accurate and efficient estimates of real-world robot behavior than Monte Carlo sampling under specified conditions, with practical approximations demonstrated on synthetic data and a robotic manipulator task.
-
HALO: Hybrid Auto-encoded Locomotion with Learned Latent Dynamics, Poincar\'e Maps, and Regions of Attraction
HALO learns latent reduced-order models with Poincaré maps for hybrid locomotion dynamics, allowing Lyapunov-based regions of attraction to be lifted from latent space to the full-order system.
-
Bounded Ratio Reinforcement Learning
BRRL derives an analytic optimal policy for regularized constrained RL that guarantees monotonic improvement and yields the BPO algorithm that matches or exceeds PPO.
-
Learning Locomotion on Discrete Terrain via Minimal Proximity Sensing
Foot-mounted proximity sensors provide pre-contact feedback that, when integrated into RL, improves quadruped traversal robustness on discrete terrain with reliable sim-to-real transfer.
-
MAPL: Multi-Objective Preference Learning for Robot Locomotion
MAPL trains quadruped locomotion policies from LLM-generated multi-objective trajectory preferences and matches or exceeds expert-designed reward performance in four environments without manual reward engineering.
-
Rotation-Aware Point-Cloud Embeddings for Vision-Based In-Hand Reorientation
Learns rotation-aware point-cloud embeddings calibrated to SO(3) geodesic error, enabling model-free RL for vision-based in-hand reorientation without pose or flow inputs.
-
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
-
HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling
HORIZON is a recoverability-governed checkpointed frontier curriculum for on-policy physical-domain scaling on quadruped locomotion that identifies three regularities: uneven widening, non-monotonic composition, and the necessity of joint on-policy interaction.
-
S-Cheetah: A Novel Quadrupedal Robot with a 3-DOF Active Spine Learning Agile Locomotion
A quadruped robot with a three-degree-of-freedom active spine reaches 6.9 m/s top speed and 7.2 rad/s turning rate via an RL framework that rewards spine engagement and gallop gaits.
-
ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation
A framework using 3D Gaussian Splatting for visual domain randomization enables robust monocular RGB-based dexterous in-hand reorientation on real hardware for multiple objects under varied lighting.
-
PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPC
PriPG-RL trains RL policies for POMDPs by distilling knowledge from a privileged anytime-feasible MPC planner into a P2P-SAC policy, improving sample efficiency and performance in partially observable robotic navigation.
-
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
-
SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows
SERNF fine-tunes dexterous manipulation policies on real hardware by pairing normalizing-flow policies with action-chunked critics and conservative off-policy RL.
-
Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
Isaac Lab is a unified GPU-native platform combining high-fidelity physics, photorealistic rendering, multi-frequency sensors, domain randomization, and learning pipelines for scalable multi-modal robot policy training.
-
RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning
RANDPOL achieves effective quadruped locomotion by training only the final linear readout of a randomly initialized and fixed neural network policy, matching PPO results with reduced parameters and enabling zero-shot sim-to-real transfer on Unitree Go2.
-
PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Control
PPO-EAL integrates exact augmented Lagrangian optimization into PPO for safe robotic control, with claimed theoretical guarantees and better empirical safety-performance tradeoffs on several robot benchmarks including sim-to-real gear assembly.
-
CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion
CTS-MoE combines a dense MoE actor with perception-based gating and a multi-critic architecture to enable adaptive perceptive locomotion on discontinuous terrain in a single-stage teacher-student training setup.
-
Redesigning Regularization for Effective Policy Smoothing
Redesigned regularization addresses implementation gaps in policy smoothing for RL, yielding smoother motions with improved performance and robustness on a quadruped robot in sim-to-real settings.
-
MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds
MARCH combines simplified-model trajectory generation with CLF-guided teacher RL and vision-policy distillation to enable stable humanoid locomotion over sparse terrain with better sample efficiency than pure model-free methods.
-
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.
-
Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion
Targeted changes to policy initialization, critic targets, and return estimation let SAC match PPO performance across legged locomotion tasks in massively parallel simulation.
-
Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
-
WaveLander: A Generalizable Hierarchical Control Framework for UAV Landing on Wave-Disturbed Platforms via Reinforcement Learning
WaveLander is a hierarchical RL control system for UAV landing on wave-disturbed platforms that uses RL for vertical velocity reference and conventional controller for attitude and lateral stability, showing robust performance in simulations.
-
Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
SDPG is a new on-policy visual RL algorithm that estimates gradients via stochastic perturbations of rollouts, achieving faster training and lower memory use than baselines on visual MuJoCo tasks while adding new robotics benchmarks and sim-to-real results.
-
Robotic Strawberry Harvesting with Robust Vision and Deep Reinforcement Learning based Sim-to-Real Control
A modified YOLO segmentation model plus sim-trained PPO control yields 84.3% overall success harvesting 281 strawberries in greenhouse trials on a real UR10e manipulator.
-
The Unified Autonomy Stack: Toward a Blueprint for Generalizable Robot Autonomy
An open-sourced Unified Autonomy Stack fuses LiDAR, radar, vision and inertial data with sampling-based planning and control barrier functions to deliver resilient autonomy on aerial and ground robots in challenging real-world settings.